From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/cbsnews.com.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/cbsnews.com.txt (limited to 'inc/3rdparty/site_config/standard/cbsnews.com.txt') diff --git a/inc/3rdparty/site_config/standard/cbsnews.com.txt b/inc/3rdparty/site_config/standard/cbsnews.com.txt new file mode 100644 index 00000000..4ba3da19 --- /dev/null +++ b/inc/3rdparty/site_config/standard/cbsnews.com.txt @@ -0,0 +1,14 @@ +date: //meta[@name="published"]/@content +date: //div[@class="timeLine"] +title: //div[@id='contentBody']//h1 +author: //dl[@class="storyBlogByline"]/dd/a +body: //div[@id='storyMediaBox'] | //div[contains(@class, 'storyText')] + +# Content Pruning +strip: //div[@class="scrollingArrows"] +strip: //div[@class="timeLine"] +strip: //dl[@class="storyBlogByline"] + +prune: no + +test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/ \ No newline at end of file -- cgit v1.2.3